PrunaAI
/

codellama-CodeLlama-7b-hf-GPTQ-8bit-smashed

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions Community

codellama-CodeLlama-7b-hf-GPTQ-8bit-smashed / generation_config.json

sharpenb's picture

dbf2f203658e8d29d295f5b1558448190dce0f6380427ba9508249ce3c18cae3

50897aa verified 12 months ago

111 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"transformers_version": "4.37.1"
	}